Triple
T29293811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miyazaki–Tokyo Haneda |
E742760
|
entity |
| Predicate | originAirportName |
P130553
|
FINISHED |
| Object | Miyazaki Airport |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Miyazaki Airport | Statement: [Miyazaki–Tokyo Haneda, originAirportName, Miyazaki Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originAirportName Context triple: [Miyazaki–Tokyo Haneda, originAirportName, Miyazaki Airport]
-
A.
originAirportICAO
Indicates the airport, identified by its ICAO code, from which a flight or journey departs.
-
B.
airportNameOrigin
chosen
Indicates the name of the airport that serves as the origin point in a trip or flight-related relationship.
-
C.
originAirportHub
Indicates that the referenced airport serves as a primary hub or main operating base for the associated airline or carrier.
-
D.
originAirportWhenMissing
Indicates the airport that should be treated as the origin when the actual origin airport information is missing.
-
E.
originAirportOnFinalFlight
Indicates the airport from which an entity’s final recorded flight departs.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f0912323c48190b9a24ef8cf359225 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69ff84df768c81908c65a1a7e33103ad |
completed | May 9, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69ff848d0af881908ee42c27a58af47e |
completed | May 9, 2026, 7:01 p.m. |
Created at: April 28, 2026, 1:04 p.m.